用单视角深度图重建物体不可见表面，比较两种新方法效果。
3D Reconstruction of non-visible surfaces of objects from a Single Depth View -- Comparative Study
- 用DeepSDF预测3D点到表面的符号距离，或用MirrorNet生成背面图像
- MirrorNet在多数类别上误差更小，速度更快，且依赖观测视角
- 适合需要快速准确重建遮挡面的机器人抓取与避障场景
场景与物体重建是机器人领域的重要问题，尤其在规划无碰撞轨迹或物体操作时。本文比较了两种从单个RGB-D相机视角重建物体不可见表面的方法。第一种方法DeepSDF通过预测给定3D空间点到物体表面的符号距离函数实现重建。第二种方法MirrorNet则通过生成物体另一侧的图像来恢复被遮挡部分。在ShapeNet数据集上的实验表明，依赖视角的MirrorNet在多数类别中具有更小的重建误差且速度更快。
原文摘要 · Abstract (English)
Scene and object reconstruction is an important problem in robotics, in particular in planning collision-free trajectories or in object manipulation. This paper compares two strategies for the reconstruction of nonvisible parts of the object surface from a single RGB-D camera view. The first method, named DeepSDF predicts the Signed Distance Transform to the object surface for a given point in 3D space. The second method, named MirrorNet reconstructs the occluded objects' parts by generating images from the other side of the observed object. Experiments performed with objects from the ShapeNet dataset, show that the view-dependent MirrorNet is faster and has smaller reconstruction errors in most categories.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。